INDEX

Explanations

statistical terminologies related to data representation and analysis

oai_token-act-pair · gpt-4o-mini Triggered by @bot

references and figures

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 invokingState

-0.49

 Italijani

-0.49

onOptions

-0.40

etzung

-0.39

@"/

-0.39

 يتيمه

-0.39

 correctes

-0.38

 balanceOf

-0.38

 BitmapFactory

-0.38

httphttps

-0.36

POSITIVE LOGITS

SOUNDBITE

0.53

Collegamenti

0.47

StringCopy

0.45

oires

0.43

 Obrador

0.43

 infographics

0.42

/***/

0.42

Cik

0.41

 slides

0.41

läufe

0.41

Activations Density 0.013%

statistical terminologies related to data representation and analysis

references and figures

No Comments

No Known Activations